Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to volumes, issues, and versions of publications or software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ersen
    -0.70
    uckland
    -0.69
    eport
    -0.65
    ught
    -0.62
    issance
    -0.60
    ndra
    -0.60
    ellery
    -0.59
    ossier
    -0.58
     Patron
    -0.57
    alty
    -0.57
    POSITIVE LOGITS
     VIII
    1.11
     8
    1.09
     4
    1.08
     VII
    1.07
     7
    1.07
     6
    1.06
     2
    1.06
     5
    1.05
     3
    1.04
     11
    1.01
    Act Density 0.143%

    No Known Activations